US20150271045A1 - Method, apparatus and system for detecting network element load imbalance - Google Patents
Method, apparatus and system for detecting network element load imbalance Download PDFInfo
- Publication number
- US20150271045A1 US20150271045A1 US14/437,337 US201314437337A US2015271045A1 US 20150271045 A1 US20150271045 A1 US 20150271045A1 US 201314437337 A US201314437337 A US 201314437337A US 2015271045 A1 US2015271045 A1 US 2015271045A1
- Authority
- US
- United States
- Prior art keywords
- load
- indicator
- performance indicator
- warning
- detecting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0805—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability
- H04L43/0817—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability by checking functioning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0876—Network utilisation, e.g. volume of load or congestion level
- H04L43/0888—Throughput
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0681—Configuration of triggering conditions
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/069—Management of faults, events, alarms or notifications using logs of notifications; Post-processing of notifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/16—Threshold monitoring
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/11—Identifying congestion
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0803—Configuration setting
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1034—Reaction to server failures by a load balancer
Definitions
- the disclosure relates to the field of network management, and in particular to a method, apparatus, and system for detecting network element (NE) load imbalance.
- NE network element
- a NE management system (centralized network management) that can manage multiple NEs at the same time enjoys increasing popularity among operators.
- a user may see an operating status and a health indicator of a NE in real time via a NE management system.
- network operating and maintaining personnel may maintain a NE with a problem in time, such that reliability of a network device may be improved.
- various processing units and NE proxy units may be deployed in a NE, and a NE manager unit and a warning unit may be deployed in a NE management system.
- a processing unit After a network service occurs, a processing unit will report data corresponding to the service to a NE proxy unit.
- the NE proxy unit may generate an important network performance indicator according to data reported by a processing unit and save the network performance indicator in a NE indicator buffer pool.
- the NE proxy unit will report an indicator in the NE indicator buffer pool to the NE manager unit.
- the NE manager unit may process a received NE indicator and save the processed NE indicator to a NE M indicator buffer pool or a NE N indicator buffer pool.
- the NE manager unit may regularly detect whether there is an abnormality (such as an overload) in a NE indicator in the NE M indicator buffer pool and the NE N indicator buffer pool. When there is such an abnormality, the NE manager unit may report in time the abnormality information to the warning unit such that a user may be warned by a warning device such as a sound and/or light alarm or the like, for example, which prompts the user to deal with the abnormality as soon as possible.
- an abnormality such as an overload
- the NE manager unit may report in time the abnormality information to the warning unit such that a user may be warned by a warning device such as a sound and/or light alarm or the like, for example, which prompts the user to deal with the abnormality as soon as possible.
- a mode may meet a most basic demand for NE operation maintenance by operating and maintaining personnel. With this mode however, detection aims only at a single NE, and a warning is not given unless there is a real problem with a NE.
- the mode is clearly insufficient to meet a user requirement of increasing concern for device automation, multi-NE correlation analysis, and failure prevention.
- most problems may occur not because all NEs are overloaded, but because of accumulating inter-NE load imbalance. NE load imbalance may be discovered via inter-NE indicator gap analysis and may be prevented in time at an initial stage of a problem.
- An embodiment herein provides a method, apparatus, and system for detecting NE load imbalance, allowing a NE management system to discover a security risk in a NE in time via automatic NE indicator gap analysis.
- a method for detecting network element (NE) load imbalance includes:
- the detecting strategy may include a load percentage threshold strategy, a constraining absolute value threshold strategy, and a load proportion strategy.
- the warning may include current indicator information, threshold information, and load proportion information.
- the performing gap analysis, according to a preset detecting strategy, on a NE performance indicator reported by a NE may include:
- Ci being a current NE performance indicator
- Di being a load proportion of a NE
- Vx (Cx/Dx ⁇ P)*100/P, with Vx being the load deviation percentage of a NE, Cx being the current NE performance indicator, Dx being the load proportion of the NE, P being the average load deviation;
- the load percentage threshold may contain a positive load percentage threshold and a negative load percentage threshold, a positive Vx may be compared with the positive load percentage threshold, and a negative Vx may be compared with the negative load percentage threshold.
- the issuing a warning when it is determined that there is such an inter-NE load imbalance may include:
- the NE overload warning may include the current indicator information, the threshold information, and the load proportion information.
- An apparatus for detecting network element (NE) load imbalance includes: a strategy configuring unit; a NE performance indicator buffer pool; a load imbalance detecting unit; and a network indicator buffer pool.
- the strategy configuring unit is configured for configuring a parameter of a detecting strategy for performing gap analysis on a NE performance indicator of a NE.
- the NE performance indicator buffer pool is configured for storing a NE performance indicator reported by a NE.
- the load imbalance detecting unit is configured for performing gap analysis, according to a preset detecting strategy, on a NE performance indicator reported by a NE, and saving a result of the gap analysis in a network indicator buffer pool.
- the network indicator buffer pool is configured for storing the result of the gap analysis.
- the detecting strategy may include a load percentage threshold strategy, a constraining absolute value threshold strategy, and a load proportion strategy.
- a system for detecting network element (NE) load imbalance includes:
- a NE configured for reporting a local NE performance indicator
- an apparatus for detecting NE load imbalance configured for performing gap analysis, according to a preset detecting strategy, on a NE performance indicator reported by a NE, and saving a result of the gap analysis in a network indicator buffer pool;
- a NE management system configured for regularly acquiring, from the network indicator buffer pool of the apparatus for detecting NE load imbalance, the result of the gap analysis, and determining, according to the acquired result of the gap analysis, whether there is an inter-NE load imbalance; issuing a warning when it is determined that there is such an inter-NE load imbalance.
- the detecting strategy may include a load percentage threshold strategy, a constraining absolute value threshold strategy, and a load proportion strategy.
- the warning may include current indicator information, threshold information, and load proportion information.
- the apparatus for detecting NE load imbalance may be configured for: determining, according to indicator information in a NE performance indicator buffer pool, whether a NE performance indicator set for any NE managed by the NE management system is complete;
- Ci being a current NE performance indicator
- Di being a load proportion of a NE
- Vx (Cx/Dx31 P)*100/P, with Vx being the load deviation percentage of a NE, Cx being the current NE performance indicator, Dx being the load proportion of the NE, P being the average load deviation;
- the load percentage threshold may contain a positive load percentage threshold and a negative load percentage threshold, a positive Vx may be compared with the positive load percentage threshold, and a negative Vx may be compared with the negative load percentage threshold.
- the NE management system may be configured for detecting whether a warning has been issued and whether the issued warning has been canceled; when a warning has been issued and has not been canceled, issuing no more NE overload warning; otherwise when no warning currently exists, issuing a new NE overload warning.
- the NE overload warning may include the current indicator information, the threshold information, and the load proportion information.
- NE load imbalance may be discovered in time in a scene of multiple management-sharing different-type NEs; thereby a user may be informed by a warning as soon as possible to eliminate in time a possible security risk at a NE; moreover, a hidden trouble may be eliminated automatically through modification using a preset automatic load strategy to improve reliability, maintainability, and stability of a network communication device.
- FIG. 1 is a schematic diagram of existing architecture for processing a NE overload.
- FIG. 2 is a flowchart of a method for detecting NE load imbalance according to an embodiment herein.
- FIG. 3 is a schematic diagram of networking for detecting NE load imbalance according to an embodiment herein.
- FIG. 4 is a schematic diagram of a structure of a system for detecting NE load imbalance according to an embodiment herein.
- FIG. 5 is a flowchart of a method for detecting NE load imbalance according to an embodiment herein.
- a method for detecting NE load imbalance may include steps as follows.
- gap analysis is performed, according to a preset detecting strategy, on a NE performance indicator reported by a NE, and a result of the gap analysis is saved in a network indicator buffer pool.
- the result of the gap analysis is acquired regularly from the network indicator buffer pool, and it is determined, according to the acquired result of the gap analysis, whether there is an inter-NE load imbalance; a warning is issued when it is determined that there is such an inter-NE load imbalance.
- the detecting strategy may include a load percentage threshold strategy, a constraining absolute value threshold strategy, and a load proportion strategy.
- the warning may include current indicator information, threshold information, and load proportion information.
- the NE performance indicator may involve two application scenes as follows.
- An indicator under detection may be a service-related indicator, such as (for the SGSN POOL) a number of attached users, an average number of activated sessions, a Gn/Gp port traffic, or the like.
- the other scene involves load balance detection among different-type NEs, such as detecting load balance between an SGSN and a Gateway GPRS Support Node (GGSN).
- An indicator under detection in general may be a hardware-related common indicator, such as CPU occupancy, memory occupancy, network traffic, or the like, or may be a service indicator for logic correlation, such as a correlation indicator between a number of SGSN attached users and a GGSN born number, or the like.
- a schematic diagram of networking for detecting NE load imbalance herein may be as shown in FIG. 3 .
- a NE may provide an indicator value corresponding to the NE.
- An apparatus for detecting NE load imbalance may be deployed as a separate device, or as an independent apparatus in a NE management system, and may perform load balance detection on some NEs of user concern.
- gap analysis may be performed, according to the preset detecting strategy, on a NE performance indicator reported by a NE in steps including those as follows.
- step A it is determined, according to indicator information in a NE performance indicator buffer pool, whether a NE performance indicator set for any NE managed by a NE management system is complete, when the NE performance indicator set is complete, the flow goes to step B, otherwise the flow goes to step C.
- step B it is determined whether the NE performance indicator of each NE has exceeded a preset constraining absolute value threshold; when the NE performance indicator of each NE has exceeded a preset constraining absolute value threshold, the flow goes to step D, otherwise the flow goes to step C.
- step C the indicator gap analysis is ended.
- step D an average load deviation is computed according to a load proportion and a NE performance indicator of a NE; the average load deviation P, as a benchmark for determining whether a NE performance indicator indicates overload of a NE, is computed according to
- Ci being a current NE performance indicator
- Di being a load proportion of a NE.
- step E a load deviation percentage of the NE is computed according to the average load deviation and a NE performance indicator of a NE according to
- Vx (Cx/Dx ⁇ P)*100/P, with Vx being the load deviation percentage of a NE, Cx being the current NE performance indicator, Dx being the load proportion of the NE, P being the NE average load deviation.
- step F the load deviation percentage of a NE is compared with a preset load percentage threshold; when the load deviation percentage of the NE exceeds the load percentage threshold, the flow goes to step G, otherwise the flow goes to step H.
- step G a performance abnormality of the NE is indicated.
- step H a normal performance state of the NE is indicated.
- the load percentage threshold may contain a positive load percentage threshold and a negative load percentage threshold; a positive Vx may be compared with the positive load percentage threshold; a negative Vx may be compared with the negative load percentage threshold.
- a warning may be issued in steps including those as follows.
- step a it is detected whether a warning has been issued and whether the issued warning has been canceled; when a warning has been issued and has not been canceled, the flow goes to step b, otherwise the flow goes to step c.
- step b no more NE overload warning is issued.
- step c a new NE overload warning is issued.
- the new NE overload warning may carry the current indicator information, the threshold information, and the load proportion information.
- the method may further include that: when a normal performance state is determined, it is detected whether a warning has been issued and whether the issued warning has been canceled. When a warning has been issued and has not been canceled, the NE overload warning is canceled, otherwise no processing is performed.
- a method for detecting NE load imbalance according to an embodiment herein, implemented by an apparatus for detecting NE load imbalance, mainly may include steps as follows.
- step 1 gap analysis is performed, according to a set detecting strategy, on a NE performance indicator reported by a NE, and a result of the gap analysis is saved in a network indicator buffer pool.
- the detecting strategy may include a load percentage threshold, a constraining absolute value threshold, and a load proportion.
- a detecting strategy set in an embodiment herein may include three parts as follows.
- the first part may be a load percentage threshold, which may include a positive load percentage threshold and a negative load percentage threshold.
- a positive load percentage threshold and a negative load percentage threshold each may be configured with multiple level thresholds each representing a load imbalance indicator threshold for a level of load imbalance warning.
- the second part may be a constraining absolute value threshold representing an indicator baseline for performing load imbalance detection. With a small amount of data to be processed, a large NE load gap may be acceptable.
- the third part may be a load proportion representing a processing capacity of a NE.
- NEs may have different processing capacities.
- a proportion/ratio thereof may not necessarily be 1:1.
- the result of the gap analysis of the NEs in the network indicator buffer pool may be sent to a NE manager unit of a NE management system.
- the NE manager unit may discover an abnormality in the result, and issue the warning to a warning unit.
- the warning information may include the current indicator information, the threshold information, and a load proportion.
- the warning information may include three parts as follows.
- the first part may be the current indicator information, such that operating and maintaining personnel may learn in real time a current NE load.
- the second part may be the current threshold information, such that operating and maintaining personnel may learn a threshold configuration when the warning is issued.
- the threshold configuration may be modified, so the warning may have to be issued matching a current threshold.
- the third part may be the load proportion information, such that operating and maintaining personnel may learn load proportion information when the warning is issued.
- the load proportion information may be adjusted as well.
- an apparatus for detecting NE load imbalance may include: a strategy configuring unit; a NE performance indicator buffer pool; a load imbalance detecting unit; and a network indicator buffer pool.
- the strategy configuring unit 32 may be configured for configuring a parameter of a detecting strategy for performing gap analysis on a NE performance indicator of a NE.
- the NE performance indicator buffer pool may be configured for storing a NE performance indicator reported by a NE.
- the load imbalance detecting unit 31 may be configured for performing gap analysis, according to a preset detecting strategy, on a NE performance indicator reported by a NE, and saving a result of the gap analysis in a network indicator buffer pool.
- the network indicator buffer pool 33 may be configured for storing the result of the gap analysis.
- the NE performance indicator buffer pool may include a first NE M indicator buffer pool 34 and a first NE N indicator buffer pool 35 .
- the first NE M indicator buffer pool 34 may be configured for storing the performance indicator of a NE M, as part of NE performance indicators on which gap analysis is to be performed.
- the first NE N indicator buffer pool 35 may be configured for storing the performance indicator of a NE N, as part of NE performance indicators on which gap analysis is to be performed.
- the detecting strategy may include a load percentage threshold strategy, a constraining absolute value threshold strategy, and a load proportion strategy.
- the load imbalance detecting unit 31 , the strategy configuring unit 32 , the network indicator buffer pool 33 , the first NE M indicator buffer pool 34 , and the first NE N indicator buffer pool 35 may be implemented by a Central Processing Unit (CPU), a Digital Signal Processor (DSP), or a Field-Programmable Gate Array (FPGA).
- CPU Central Processing Unit
- DSP Digital Signal Processor
- FPGA Field-Programmable Gate Array
- a system for detecting NE load imbalance may include:
- a NE 10 configured for reporting a local NE performance indicator
- an apparatus for detecting NE load imbalance 30 configured for performing gap analysis, according to a preset detecting strategy, on a NE performance indicator reported by a NE, and saving a result of the gap analysis in a network indicator buffer pool;
- a NE management system 20 configured for regularly acquiring, from the network indicator buffer pool of the apparatus for detecting NE load imbalance 30 , the result of the gap analysis, and determining, according to the acquired result of the gap analysis, whether there is an inter-NE load imbalance; issuing a warning when it is determined that there is such an inter-NE load imbalance.
- the detecting strategy may include a load percentage threshold strategy, a constraining absolute value threshold strategy, and a load proportion strategy.
- the warning may include current indicator information, threshold information, and load proportion information.
- the apparatus for detecting NE load imbalance 30 may be configured for determining, according to indicator information in a NE performance indicator buffer pool, whether a NE performance indicator set for any NE managed by the NE management system is complete;
- Ci being a current NE performance indicator
- Di being a load proportion of a NE
- Vx (Cx/Dx ⁇ P)*100/P, with Vx being the load deviation percentage of a NE, Cx being the current NE performance indicator, Dx being the load proportion of the NE, P being the average load deviation;
- the load percentage threshold contains a positive load percentage threshold and a negative load percentage threshold, a positive Vx is compared with the positive load percentage threshold, and a negative Vx is compared with the negative load percentage threshold.
- the NE management system 20 may be configured for detecting whether a warning has been issued and whether the issued warning has been canceled; when a warning has been issued and has not been canceled, issuing no more NE overload warning; otherwise when no warning currently exists, issuing a new NE overload warning.
- the new NE overload warning may carry the current indicator information, the threshold information, and the load proportion information.
- the load imbalance detecting unit 31 and the strategy configuring unit 32 are connected to each other; the load imbalance detecting unit 31 and the network indicator buffer pool 33 are connected to each other; the network indicator buffer pool 33 , the first NE M indicator buffer pool 34 , and the first NE N indicator buffer pool 35 are connected to each other.
- the load imbalance detecting unit 31 may be configured for performing gap analysis, according to a configured detecting strategy, on a NE performance indicator reported by a NE, and saving a result of the gap analysis in a network indicator buffer pool 33 .
- the strategy configuring unit 32 may be configured for configuring and storing a parameter of a detecting strategy for load imbalance detection.
- the network indicator buffer pool 33 may be configured for saving the result of NE load balance detection obtained by gap analysis, and sending the result of the gap analysis to the NE management system 20 .
- the first NE M indicator buffer pool 34 may be configured for saving the result of load gap analysis for the NE M.
- the first NE N indicator buffer pool 35 may be configured for saving the result of load gap analysis for the NE N.
- the processing unit 11 the NE proxy unit 12 , and the NE indicator buffer pool 13 may be connected to the load imbalance detecting unit 31 .
- the processing unit 11 may be configured for detecting a NE operating status; when a service occurs on a network, reporting, to the NE proxy unit 12 , data corresponding to the service.
- the NE proxy 12 may be connected to the processing unit 11 and the load imbalance detecting unit 31 , and may be configured for receiving data reported by the processing unit 11 and extracting a NE performance indicator from the received data, and then caching the extracted indicator in the NE indicator buffer pool 13 of the NE, and when appropriate (at regular intervals), reporting the NE performance indicator of the NE to the load imbalance detecting unit 31 for performance indicator gap analysis.
- the original NE performance indicator of the NE will also be reported to the NE management system 20 for single NE indicator analysis.
- the NE indicator buffer pool 13 may be connected to the NE proxy unit 12 , and may be configured for NE performance indicator caching.
- the NE management system 20 may be connected to the network indicator buffer pool 33 and may include: a NE manager unit 21 , a second NE M indicator buffer pool 22 , a second NE N indicator buffer pool 23 , and a warning unit 24 .
- the NE manager unit 21 may be connected to the NE proxy 12 and the network indicator buffer pool 33 , and be configured for receiving the NE performance indicator of a single NE sent by the NE proxy 12 , caching the received indicator in the second NE M indicator buffer pool and the second NE N indicator buffer pool, analyzing the cached indicator; acquiring and analyzing the result of the NE gap analysis in the network indicator buffer pool 33 ; issuing a warning to the warning unit 24 when an abnormality is discovered.
- the second NE M indicator buffer pool 22 may be connected to the NE manager unit 21 , and be configured for caching the NE indicator of the NE M.
- the second NE N indicator buffer pool 23 may be connected to the NE manager unit 21 , and be configured for caching the NE indicator of the NE N.
- the warning unit 24 may be connected to the NE manager unit 21 , and be configured for displaying the warning sent by the NE manager unit 21 and implementing a warning such as by sound and/or light.
- the NE manager unit 21 , the second NE M indicator buffer pool 22 , the second NE N indicator buffer pool 23 , and the warning unit 24 may be implemented by a CPU, a DSP, or an FPGA.
- FIG. 5 is a flowchart of a method for detecting NE load imbalance according to an embodiment herein, the method mainly may include steps as follows.
- a detection flow thereof may include steps as follows.
- a NE proxy unit 12 reports a NE performance indicator of a local NE to a load imbalance detecting unit 31 .
- the indicator must contain a valid performance indicator value.
- step 402 the load imbalance detecting unit 31 detects, according to a strategy, whether a reported NE indicator set is complete, that is, whether each strategy monitored NE has reported its performance indicator; if so, the flow goes to step 403 ; otherwise, the flow ends.
- step 403 the load imbalance detecting unit 31 detects, according to a strategy, whether a reported NE indicator exceeds the constraining absolute value threshold according to a strategy; if so, the flow goes to step 404 ; otherwise, the flow ends.
- the Ci may be the current value of a NE indicator under detection.
- the Di may be the load proportion of a NE.
- step 405 the load imbalance detecting unit 31 checks whether detection has been performed for each NE indicator; if so, the flow ends; otherwise, the flow goes to step 406 .
- step 406 the load imbalance detecting unit 31 extracts a NE indicator for which detection is yet to be performed.
- the C may be the current detecting indicator of the NE.
- the D may be the load proportion of the NE.
- the P may be the average load deviation.
- step 408 the load imbalance detecting unit 31 detects whether the load deviation percentage of the NE exceeds a load percentage threshold configured in a strategy; if so, the flow goes to step 409 ; otherwise, the flow goes to step 411 .
- step 409 the load imbalance detecting unit 31 indicates the NE indicator of the NE as abnormal in a network indicator buffer pool 33 ; the flow returns to step 405 .
- step 410 the load imbalance detecting unit 31 sets the NE indicator in the network indicator buffer pool 33 as expired.
- step 411 the load imbalance detecting unit 31 indicates the NE indicator of the NE as normal in the network indicator buffer pool 33 ; the flow returns to step 405 .
- a processing flow in the method may include steps as follows.
- a NE manager unit 21 extracts, from the network indicator buffer pool 33 , the result of the NE gap analysis, and analyzes the same; the flow goes to step 413 when an abnormality is discovered; otherwise, the flow goes to step 414 .
- step 413 the NE manager unit 21 extracts a NE indicator from the network indicator buffer pool 33 , detects whether a corresponding warning has been issued and whether the issued warning has been canceled; when the issued warning exists, the flow ends; otherwise, the flow goes to step 415 .
- step 414 the NE manager unit 21 extracts, from the network indicator buffer pool 33 , the NE indicator, detecting whether a corresponding warning has been issued and whether the issued warning has been canceled; if so, the flow goes to step 416 ; otherwise, flow ends.
- the NE manager unit 21 issues a new NE load imbalance warning to the warning unit 24 .
- the warning may carry current indicator information, threshold information, and load proportion information.
- step 416 the NE manager unit 21 issues a warning removing message to the warning unit 24 to cancel the NE load imbalance warning.
- load imbalance detection may be performed on similar indicators in a NE to automatically uncover whether there is a logic unit load imbalance within the NE.
- the disclosure may include further embodiments.
- the load imbalance detecting unit may be connected, not to the NE proxy unit, but directly to the NE manager unit.
- those skilled in the art may make various modifications and variations according to the disclosure without departing from the spirit and essence of the disclosure. Such modifications and variations each should fall within the scope of the disclosure.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Environmental & Geological Engineering (AREA)
- Debugging And Monitoring (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Computer And Data Communications (AREA)
Abstract
Description
- The disclosure relates to the field of network management, and in particular to a method, apparatus, and system for detecting network element (NE) load imbalance.
- In the field of network communication, as an amount of communicated information increases, there is an increasing user demand for communication products of high stability and high performance. This puts a higher requirement on reliability of a communication device.
- At present, a NE management system (centralized network management) that can manage multiple NEs at the same time enjoys increasing popularity among operators. A user may see an operating status and a health indicator of a NE in real time via a NE management system. Thus, network operating and maintaining personnel may maintain a NE with a problem in time, such that reliability of a network device may be improved.
- As shown in
FIG. 1 , with existing NE management system architecture, various processing units and NE proxy units may be deployed in a NE, and a NE manager unit and a warning unit may be deployed in a NE management system. After a network service occurs, a processing unit will report data corresponding to the service to a NE proxy unit. The NE proxy unit may generate an important network performance indicator according to data reported by a processing unit and save the network performance indicator in a NE indicator buffer pool. When appropriate (at regular intervals), the NE proxy unit will report an indicator in the NE indicator buffer pool to the NE manager unit. The NE manager unit may process a received NE indicator and save the processed NE indicator to a NE M indicator buffer pool or a NE N indicator buffer pool. The NE manager unit may regularly detect whether there is an abnormality (such as an overload) in a NE indicator in the NE M indicator buffer pool and the NE N indicator buffer pool. When there is such an abnormality, the NE manager unit may report in time the abnormality information to the warning unit such that a user may be warned by a warning device such as a sound and/or light alarm or the like, for example, which prompts the user to deal with the abnormality as soon as possible. - Under normal circumstances, such a mode may meet a most basic demand for NE operation maintenance by operating and maintaining personnel. With this mode however, detection aims only at a single NE, and a warning is not given unless there is a real problem with a NE. The mode is clearly insufficient to meet a user requirement of increasing concern for device automation, multi-NE correlation analysis, and failure prevention. In actual network operation, most problems may occur not because all NEs are overloaded, but because of accumulating inter-NE load imbalance. NE load imbalance may be discovered via inter-NE indicator gap analysis and may be prevented in time at an initial stage of a problem.
- It may be affirmed that manual indicator gap analysis by operating and maintaining personnel is clearly inefficient, by which a problem may not be discovered in real time. With increasing complication and diversification of NEs managed by a NE management system, there are more and more important inter-NE indicators and an increasingly complicated inter-NE relation, such that an aforementioned problem becomes more prominent. Therefore, a NE management system is facing a severe test in terms of ensuring reliability, availability, maintainability, and stability of a NE.
- An embodiment herein provides a method, apparatus, and system for detecting NE load imbalance, allowing a NE management system to discover a security risk in a NE in time via automatic NE indicator gap analysis.
- To this end, a technical solution according to an embodiment herein may be implemented as follows.
- A method for detecting network element (NE) load imbalance includes:
- performing gap analysis, according to a preset detecting strategy, on a NE performance indicator reported by a NE, and saving a result of the gap analysis in a network indicator buffer pool; and
- regularly acquiring, from the network indicator buffer pool, the result of the gap analysis, and determining, according to the acquired result of the gap analysis, whether there is an inter-NE load imbalance; issuing a warning when it is determined that there is such an inter-NE load imbalance.
- The detecting strategy may include a load percentage threshold strategy, a constraining absolute value threshold strategy, and a load proportion strategy.
- The warning may include current indicator information, threshold information, and load proportion information.
- The performing gap analysis, according to a preset detecting strategy, on a NE performance indicator reported by a NE may include:
- determining, according to indicator information in a NE performance indicator buffer pool, whether a NE performance indicator set for any NE managed by a NE management system is complete;
- when the NE performance indicator set is complete, determining whether the NE performance indicator of each NE has exceeded a preset constraining absolute value threshold;
- when the NE performance indicator of each NE has exceeded a preset constraining absolute value threshold, computing, according to a load proportion and a NE performance indicator of a NE, an average load deviation, wherein the average load deviation P, as a benchmark for determining whether a NE performance indicator indicates overload of a NE, is computed according to
- P=ΣCi/ΣDi, with Ci being a current NE performance indicator, Di being a load proportion of a NE;
- computing, according to the average load deviation and a NE performance indicator of a NE, a load deviation percentage of the NE according to
- Vx=(Cx/Dx−P)*100/P, with Vx being the load deviation percentage of a NE, Cx being the current NE performance indicator, Dx being the load proportion of the NE, P being the average load deviation;
- comparing the load deviation percentage of a NE with a preset load percentage threshold; when the load deviation percentage of the NE exceeds the load percentage threshold, indicating a performance abnormality of the NE; when the load deviation percentage of the NE does not exceed the load percentage threshold, indicating a normal performance state of the NE.
- The load percentage threshold may contain a positive load percentage threshold and a negative load percentage threshold, a positive Vx may be compared with the positive load percentage threshold, and a negative Vx may be compared with the negative load percentage threshold.
- The issuing a warning when it is determined that there is such an inter-NE load imbalance may include:
- detecting whether a warning has been issued and whether the issued warning has been canceled; when a warning has been issued and has not been canceled, issuing no more NE overload warning; otherwise when no warning currently exists, issuing a new NE overload warning. The NE overload warning may include the current indicator information, the threshold information, and the load proportion information.
- An apparatus for detecting network element (NE) load imbalance includes: a strategy configuring unit; a NE performance indicator buffer pool; a load imbalance detecting unit; and a network indicator buffer pool.
- The strategy configuring unit is configured for configuring a parameter of a detecting strategy for performing gap analysis on a NE performance indicator of a NE.
- The NE performance indicator buffer pool is configured for storing a NE performance indicator reported by a NE.
- The load imbalance detecting unit is configured for performing gap analysis, according to a preset detecting strategy, on a NE performance indicator reported by a NE, and saving a result of the gap analysis in a network indicator buffer pool.
- The network indicator buffer pool is configured for storing the result of the gap analysis.
- The detecting strategy may include a load percentage threshold strategy, a constraining absolute value threshold strategy, and a load proportion strategy.
- A system for detecting network element (NE) load imbalance includes:
- a NE configured for reporting a local NE performance indicator;
- an apparatus for detecting NE load imbalance configured for performing gap analysis, according to a preset detecting strategy, on a NE performance indicator reported by a NE, and saving a result of the gap analysis in a network indicator buffer pool; and
- a NE management system configured for regularly acquiring, from the network indicator buffer pool of the apparatus for detecting NE load imbalance, the result of the gap analysis, and determining, according to the acquired result of the gap analysis, whether there is an inter-NE load imbalance; issuing a warning when it is determined that there is such an inter-NE load imbalance.
- The detecting strategy may include a load percentage threshold strategy, a constraining absolute value threshold strategy, and a load proportion strategy.
- The warning may include current indicator information, threshold information, and load proportion information.
- The apparatus for detecting NE load imbalance may be configured for: determining, according to indicator information in a NE performance indicator buffer pool, whether a NE performance indicator set for any NE managed by the NE management system is complete;
- when the NE performance indicator set is complete, determining whether the NE performance indicator of each NE has exceeded a preset constraining absolute value threshold;
- when the NE performance indicator of each NE has exceeded a preset constraining absolute value threshold, computing, according to a load proportion and a NE performance indicator of a NE, an average load deviation, wherein the average load deviation P, as a benchmark for determining whether a NE performance indicator indicates overload of a NE, is computed according to
- P=ΣCi/ΣDi, with Ci being a current NE performance indicator, Di being a load proportion of a NE;
- computing, according to the average load deviation and a NE performance indicator of a NE, a load deviation percentage of the NE according to
- Vx=(Cx/Dx31 P)*100/P, with Vx being the load deviation percentage of a NE, Cx being the current NE performance indicator, Dx being the load proportion of the NE, P being the average load deviation; and
- comparing the load deviation percentage of a NE with a preset load percentage threshold; when the load deviation percentage of the NE exceeds the load percentage threshold, indicating a performance abnormality of the NE; when the load deviation percentage of the NE does not exceed the load percentage threshold, indicating a normal performance state of the NE.
- The load percentage threshold may contain a positive load percentage threshold and a negative load percentage threshold, a positive Vx may be compared with the positive load percentage threshold, and a negative Vx may be compared with the negative load percentage threshold.
- The NE management system may be configured for detecting whether a warning has been issued and whether the issued warning has been canceled; when a warning has been issued and has not been canceled, issuing no more NE overload warning; otherwise when no warning currently exists, issuing a new NE overload warning. The NE overload warning may include the current indicator information, the threshold information, and the load proportion information.
- It may be seen that with a technical solution according to an embodiment herein, by computing an average load deviation and a load deviation percentage and comparison with a threshold, NE load imbalance may be discovered in time in a scene of multiple management-sharing different-type NEs; thereby a user may be informed by a warning as soon as possible to eliminate in time a possible security risk at a NE; moreover, a hidden trouble may be eliminated automatically through modification using a preset automatic load strategy to improve reliability, maintainability, and stability of a network communication device.
-
FIG. 1 is a schematic diagram of existing architecture for processing a NE overload. -
FIG. 2 is a flowchart of a method for detecting NE load imbalance according to an embodiment herein. -
FIG. 3 is a schematic diagram of networking for detecting NE load imbalance according to an embodiment herein. -
FIG. 4 is a schematic diagram of a structure of a system for detecting NE load imbalance according to an embodiment herein. -
FIG. 5 is a flowchart of a method for detecting NE load imbalance according to an embodiment herein. - A technical solution herein is further elaborated below with reference to the drawings and embodiments.
- As shown in
FIG. 2 , a method for detecting NE load imbalance according to an embodiment herein may include steps as follows. - In S100, gap analysis is performed, according to a preset detecting strategy, on a NE performance indicator reported by a NE, and a result of the gap analysis is saved in a network indicator buffer pool.
- In S200, the result of the gap analysis is acquired regularly from the network indicator buffer pool, and it is determined, according to the acquired result of the gap analysis, whether there is an inter-NE load imbalance; a warning is issued when it is determined that there is such an inter-NE load imbalance.
- In the step S100, the detecting strategy may include a load percentage threshold strategy, a constraining absolute value threshold strategy, and a load proportion strategy.
- In the step S200, the warning may include current indicator information, threshold information, and load proportion information.
- The NE performance indicator may involve two application scenes as follows.
- One scene involves load balance detection among same-type NEs, such as load balance detection among MSCs in a Mobile Switching Center (MSC) pool or load balance detection among SGSNs in a Serving GPRS support Node (SGSN) POOL. An indicator under detection may be a service-related indicator, such as (for the SGSN POOL) a number of attached users, an average number of activated sessions, a Gn/Gp port traffic, or the like.
- The other scene involves load balance detection among different-type NEs, such as detecting load balance between an SGSN and a Gateway GPRS Support Node (GGSN). An indicator under detection in general may be a hardware-related common indicator, such as CPU occupancy, memory occupancy, network traffic, or the like, or may be a service indicator for logic correlation, such as a correlation indicator between a number of SGSN attached users and a GGSN born number, or the like. A schematic diagram of networking for detecting NE load imbalance herein may be as shown in
FIG. 3 . A NE may provide an indicator value corresponding to the NE. An apparatus for detecting NE load imbalance may be deployed as a separate device, or as an independent apparatus in a NE management system, and may perform load balance detection on some NEs of user concern. - In the step S100, gap analysis may be performed, according to the preset detecting strategy, on a NE performance indicator reported by a NE in steps including those as follows.
- In step A, it is determined, according to indicator information in a NE performance indicator buffer pool, whether a NE performance indicator set for any NE managed by a NE management system is complete, when the NE performance indicator set is complete, the flow goes to step B, otherwise the flow goes to step C.
- In step B, it is determined whether the NE performance indicator of each NE has exceeded a preset constraining absolute value threshold; when the NE performance indicator of each NE has exceeded a preset constraining absolute value threshold, the flow goes to step D, otherwise the flow goes to step C.
- In step C, the indicator gap analysis is ended.
- In step D, an average load deviation is computed according to a load proportion and a NE performance indicator of a NE; the average load deviation P, as a benchmark for determining whether a NE performance indicator indicates overload of a NE, is computed according to
- P=ΣCi/ΣDi, with Ci being a current NE performance indicator, Di being a load proportion of a NE.
- In step E, a load deviation percentage of the NE is computed according to the average load deviation and a NE performance indicator of a NE according to
- Vx=(Cx/Dx−P)*100/P, with Vx being the load deviation percentage of a NE, Cx being the current NE performance indicator, Dx being the load proportion of the NE, P being the NE average load deviation.
- In step F, the load deviation percentage of a NE is compared with a preset load percentage threshold; when the load deviation percentage of the NE exceeds the load percentage threshold, the flow goes to step G, otherwise the flow goes to step H.
- In step G, a performance abnormality of the NE is indicated.
- In step H, a normal performance state of the NE is indicated.
- in the step F, the load percentage threshold may contain a positive load percentage threshold and a negative load percentage threshold; a positive Vx may be compared with the positive load percentage threshold; a negative Vx may be compared with the negative load percentage threshold.
- In the step S200, when it is determined that there is such an inter-NE load imbalance, a warning may be issued in steps including those as follows.
- In step a, it is detected whether a warning has been issued and whether the issued warning has been canceled; when a warning has been issued and has not been canceled, the flow goes to step b, otherwise the flow goes to step c.
- In step b, no more NE overload warning is issued.
- In step c, a new NE overload warning is issued. The new NE overload warning may carry the current indicator information, the threshold information, and the load proportion information.
- The method may further include that: when a normal performance state is determined, it is detected whether a warning has been issued and whether the issued warning has been canceled. When a warning has been issued and has not been canceled, the NE overload warning is canceled, otherwise no processing is performed.
- A method for detecting NE load imbalance according to an embodiment herein, implemented by an apparatus for detecting NE load imbalance, mainly may include steps as follows.
- In step 1, gap analysis is performed, according to a set detecting strategy, on a NE performance indicator reported by a NE, and a result of the gap analysis is saved in a network indicator buffer pool. The detecting strategy may include a load percentage threshold, a constraining absolute value threshold, and a load proportion.
- A detecting strategy set in an embodiment herein may include three parts as follows.
- The first part may be a load percentage threshold, which may include a positive load percentage threshold and a negative load percentage threshold. In addition, a positive load percentage threshold and a negative load percentage threshold each may be configured with multiple level thresholds each representing a load imbalance indicator threshold for a level of load imbalance warning.
- The second part may be a constraining absolute value threshold representing an indicator baseline for performing load imbalance detection. With a small amount of data to be processed, a large NE load gap may be acceptable.
- The third part may be a load proportion representing a processing capacity of a NE. Depending on different software/hardware configurations, NEs may have different processing capacities. A proportion/ratio thereof may not necessarily be 1:1.
- In step 2, the result of the gap analysis of the NEs in the network indicator buffer pool may be sent to a NE manager unit of a NE management system. The NE manager unit may discover an abnormality in the result, and issue the warning to a warning unit. The warning information may include the current indicator information, the threshold information, and a load proportion.
- In an embodiment herein, the warning information may include three parts as follows.
- The first part may be the current indicator information, such that operating and maintaining personnel may learn in real time a current NE load.
- The second part may be the current threshold information, such that operating and maintaining personnel may learn a threshold configuration when the warning is issued. The threshold configuration may be modified, so the warning may have to be issued matching a current threshold.
- The third part may be the load proportion information, such that operating and maintaining personnel may learn load proportion information when the warning is issued. The load proportion information may be adjusted as well.
- According to an embodiment herein, an apparatus for detecting NE load imbalance, as shown in
FIG. 4 , may include: a strategy configuring unit; a NE performance indicator buffer pool; a load imbalance detecting unit; and a network indicator buffer pool. - The
strategy configuring unit 32 may be configured for configuring a parameter of a detecting strategy for performing gap analysis on a NE performance indicator of a NE. - The NE performance indicator buffer pool may be configured for storing a NE performance indicator reported by a NE.
- The load
imbalance detecting unit 31 may be configured for performing gap analysis, according to a preset detecting strategy, on a NE performance indicator reported by a NE, and saving a result of the gap analysis in a network indicator buffer pool. - The network
indicator buffer pool 33 may be configured for storing the result of the gap analysis. - For example, in the embodiment, the NE performance indicator buffer pool may include a first NE M
indicator buffer pool 34 and a first NE Nindicator buffer pool 35. - The first NE M
indicator buffer pool 34 may be configured for storing the performance indicator of a NE M, as part of NE performance indicators on which gap analysis is to be performed. - The first NE N
indicator buffer pool 35 may be configured for storing the performance indicator of a NE N, as part of NE performance indicators on which gap analysis is to be performed. - The detecting strategy may include a load percentage threshold strategy, a constraining absolute value threshold strategy, and a load proportion strategy.
- In an actual application, the load
imbalance detecting unit 31, thestrategy configuring unit 32, the networkindicator buffer pool 33, the first NE Mindicator buffer pool 34, and the first NE Nindicator buffer pool 35 may be implemented by a Central Processing Unit (CPU), a Digital Signal Processor (DSP), or a Field-Programmable Gate Array (FPGA). - As shown in
FIG. 4 , according to an embodiment herein, a system for detecting NE load imbalance may include: - a
NE 10 configured for reporting a local NE performance indicator; - an apparatus for detecting
NE load imbalance 30 configured for performing gap analysis, according to a preset detecting strategy, on a NE performance indicator reported by a NE, and saving a result of the gap analysis in a network indicator buffer pool; and - a
NE management system 20 configured for regularly acquiring, from the network indicator buffer pool of the apparatus for detectingNE load imbalance 30, the result of the gap analysis, and determining, according to the acquired result of the gap analysis, whether there is an inter-NE load imbalance; issuing a warning when it is determined that there is such an inter-NE load imbalance. - The detecting strategy may include a load percentage threshold strategy, a constraining absolute value threshold strategy, and a load proportion strategy.
- The warning may include current indicator information, threshold information, and load proportion information.
- The apparatus for detecting
NE load imbalance 30 may be configured for determining, according to indicator information in a NE performance indicator buffer pool, whether a NE performance indicator set for any NE managed by the NE management system is complete; - when the NE performance indicator set is complete, determining whether the NE performance indicator of each NE has exceeded a preset constraining absolute value threshold;
- when the NE performance indicator of each NE has exceeded a preset constraining absolute value threshold, computing, according to a load proportion and a NE performance indicator of a NE, an average load deviation, wherein the average load deviation P, as a benchmark for determining whether a NE performance indicator indicates overload of a NE, is computed according to
- P=ΣCi/ΣDi, with Ci being a current NE performance indicator, Di being a load proportion of a NE;
- computing, according to the average load deviation and a NE performance indicator of a NE, a load deviation percentage of the NE according to
- Vx=(Cx/Dx−P)*100/P, with Vx being the load deviation percentage of a NE, Cx being the current NE performance indicator, Dx being the load proportion of the NE, P being the average load deviation;
- comparing the load deviation percentage of a NE with a preset load percentage threshold;
- when the load deviation percentage of the NE exceeds the load percentage threshold, indicating a performance abnormality of the NE, otherwise indicating a normal performance state of the NE.
- The load percentage threshold contains a positive load percentage threshold and a negative load percentage threshold, a positive Vx is compared with the positive load percentage threshold, and a negative Vx is compared with the negative load percentage threshold.
- The
NE management system 20 may be configured for detecting whether a warning has been issued and whether the issued warning has been canceled; when a warning has been issued and has not been canceled, issuing no more NE overload warning; otherwise when no warning currently exists, issuing a new NE overload warning. The new NE overload warning may carry the current indicator information, the threshold information, and the load proportion information. - In the embodiment, as shown in
FIG. 4 , in the apparatus for detecting NE load imbalance 30 (for implementing the method for detecting NE load imbalance shown inFIG. 2 ), the loadimbalance detecting unit 31 and thestrategy configuring unit 32 are connected to each other; the loadimbalance detecting unit 31 and the networkindicator buffer pool 33 are connected to each other; the networkindicator buffer pool 33, the first NE Mindicator buffer pool 34, and the first NE Nindicator buffer pool 35 are connected to each other. - The load
imbalance detecting unit 31 may be configured for performing gap analysis, according to a configured detecting strategy, on a NE performance indicator reported by a NE, and saving a result of the gap analysis in a networkindicator buffer pool 33. - The
strategy configuring unit 32 may be configured for configuring and storing a parameter of a detecting strategy for load imbalance detection. - The network
indicator buffer pool 33 may be configured for saving the result of NE load balance detection obtained by gap analysis, and sending the result of the gap analysis to theNE management system 20. - The first NE M
indicator buffer pool 34 may be configured for saving the result of load gap analysis for the NE M. - the first NE N
indicator buffer pool 35 may be configured for saving the result of load gap analysis for the NE N. - In the
NE 10, theprocessing unit 11, theNE proxy unit 12, and the NEindicator buffer pool 13 may be connected to the loadimbalance detecting unit 31. - The
processing unit 11 may be configured for detecting a NE operating status; when a service occurs on a network, reporting, to theNE proxy unit 12, data corresponding to the service. - The
NE proxy 12 may be connected to theprocessing unit 11 and the loadimbalance detecting unit 31, and may be configured for receiving data reported by theprocessing unit 11 and extracting a NE performance indicator from the received data, and then caching the extracted indicator in the NEindicator buffer pool 13 of the NE, and when appropriate (at regular intervals), reporting the NE performance indicator of the NE to the loadimbalance detecting unit 31 for performance indicator gap analysis. The original NE performance indicator of the NE will also be reported to theNE management system 20 for single NE indicator analysis. - The NE
indicator buffer pool 13 may be connected to theNE proxy unit 12, and may be configured for NE performance indicator caching. - The
NE management system 20 may be connected to the networkindicator buffer pool 33 and may include: aNE manager unit 21, a second NE Mindicator buffer pool 22, a second NE Nindicator buffer pool 23, and awarning unit 24. - The
NE manager unit 21 may be connected to theNE proxy 12 and the networkindicator buffer pool 33, and be configured for receiving the NE performance indicator of a single NE sent by theNE proxy 12, caching the received indicator in the second NE M indicator buffer pool and the second NE N indicator buffer pool, analyzing the cached indicator; acquiring and analyzing the result of the NE gap analysis in the networkindicator buffer pool 33; issuing a warning to thewarning unit 24 when an abnormality is discovered. - The second NE M
indicator buffer pool 22 may be connected to theNE manager unit 21, and be configured for caching the NE indicator of the NE M. - The second NE N
indicator buffer pool 23 may be connected to theNE manager unit 21, and be configured for caching the NE indicator of the NE N. - The
warning unit 24 may be connected to theNE manager unit 21, and be configured for displaying the warning sent by theNE manager unit 21 and implementing a warning such as by sound and/or light. - In an actual application, the
NE manager unit 21, the second NE Mindicator buffer pool 22, the second NE Nindicator buffer pool 23, and thewarning unit 24 may be implemented by a CPU, a DSP, or an FPGA. - The method for detecting NE load imbalance according to an embodiment herein may be elaborated below with reference to the apparatus for detecting NE load balance shown in
FIG. 4 . As shown inFIG. 5 , which is a flowchart of a method for detecting NE load imbalance according to an embodiment herein, the method mainly may include steps as follows. - A detection flow thereof may include steps as follows.
- In
step 401, aNE proxy unit 12 reports a NE performance indicator of a local NE to a loadimbalance detecting unit 31. The indicator must contain a valid performance indicator value. - In
step 402, the loadimbalance detecting unit 31 detects, according to a strategy, whether a reported NE indicator set is complete, that is, whether each strategy monitored NE has reported its performance indicator; if so, the flow goes to step 403; otherwise, the flow ends. - In
step 403, the loadimbalance detecting unit 31 detects, according to a strategy, whether a reported NE indicator exceeds the constraining absolute value threshold according to a strategy; if so, the flow goes to step 404; otherwise, the flow ends. - In
step 404, the loadimbalance detecting unit 31 computes, according to a NE indicator value and a strategy-configured NE load proportion, an average load deviation P=ΣCi/ΣDi. The Ci may be the current value of a NE indicator under detection. The Di may be the load proportion of a NE. - In
step 405, the loadimbalance detecting unit 31 checks whether detection has been performed for each NE indicator; if so, the flow ends; otherwise, the flow goes to step 406. - In
step 406, the loadimbalance detecting unit 31 extracts a NE indicator for which detection is yet to be performed. - In
step 407, the loadimbalance detecting unit 31 computes a load deviation percentage V=(C/D−P)*100/ P. The C may be the current detecting indicator of the NE. The D may be the load proportion of the NE. The P may be the average load deviation. - In
step 408, the loadimbalance detecting unit 31 detects whether the load deviation percentage of the NE exceeds a load percentage threshold configured in a strategy; if so, the flow goes to step 409; otherwise, the flow goes to step 411. - In
step 409, the loadimbalance detecting unit 31 indicates the NE indicator of the NE as abnormal in a networkindicator buffer pool 33; the flow returns to step 405. - In
step 410, the loadimbalance detecting unit 31 sets the NE indicator in the networkindicator buffer pool 33 as expired. - In
step 411, the loadimbalance detecting unit 31 indicates the NE indicator of the NE as normal in the networkindicator buffer pool 33; the flow returns to step 405. - A processing flow in the method may include steps as follows.
- In
step 412, aNE manager unit 21 extracts, from the networkindicator buffer pool 33, the result of the NE gap analysis, and analyzes the same; the flow goes to step 413 when an abnormality is discovered; otherwise, the flow goes to step 414. - In
step 413, theNE manager unit 21 extracts a NE indicator from the networkindicator buffer pool 33, detects whether a corresponding warning has been issued and whether the issued warning has been canceled; when the issued warning exists, the flow ends; otherwise, the flow goes to step 415. - In
step 414, theNE manager unit 21 extracts, from the networkindicator buffer pool 33, the NE indicator, detecting whether a corresponding warning has been issued and whether the issued warning has been canceled; if so, the flow goes to step 416; otherwise, flow ends. - In
step 415, theNE manager unit 21 issues a new NE load imbalance warning to thewarning unit 24. The warning may carry current indicator information, threshold information, and load proportion information. - In
step 416, theNE manager unit 21 issues a warning removing message to thewarning unit 24 to cancel the NE load imbalance warning. - Note that another similar problem may be solved with an embodiment herein. For example, load imbalance detection may be performed on similar indicators in a NE to automatically uncover whether there is a logic unit load imbalance within the NE.
- The disclosure may include further embodiments. For example, the load imbalance detecting unit may be connected, not to the NE proxy unit, but directly to the NE manager unit. In general, those skilled in the art may make various modifications and variations according to the disclosure without departing from the spirit and essence of the disclosure. Such modifications and variations each should fall within the scope of the disclosure.
- What described are merely embodiments of the disclosure, and are not intended to limit the scope of the disclosure. All equivalent structures or flow variations made using content of the specification and accompanying drawings of the disclosure, or direct or indirect application in another related technical field, likewise fall within the scope of the disclosure.
Claims (14)
Applications Claiming Priority (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210404787.9 | 2012-10-22 | ||
CN201210404787 | 2012-10-22 | ||
CN201210404787.9A CN102932170B (en) | 2012-10-22 | 2012-10-22 | Network element load inequality detection processing method, device and system thereof |
PCT/CN2013/084512 WO2014063557A1 (en) | 2012-10-22 | 2013-09-27 | Method, apparatus and system for detecting network element load imbalance |
Publications (2)
Publication Number | Publication Date |
---|---|
US20150271045A1 true US20150271045A1 (en) | 2015-09-24 |
US9674065B2 US9674065B2 (en) | 2017-06-06 |
Family
ID=47646877
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/437,337 Expired - Fee Related US9674065B2 (en) | 2012-10-22 | 2013-09-27 | Method, apparatus and system for detecting network element load imbalance |
Country Status (4)
Country | Link |
---|---|
US (1) | US9674065B2 (en) |
EP (1) | EP2899918A4 (en) |
CN (1) | CN102932170B (en) |
WO (1) | WO2014063557A1 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11157323B2 (en) * | 2019-01-10 | 2021-10-26 | International Business Machines Corporation | Multiple metric based load prediction and resource allocation in an active stream processing job |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102932170B (en) * | 2012-10-22 | 2016-06-22 | 中兴通讯股份有限公司 | Network element load inequality detection processing method, device and system thereof |
CN105323100B (en) * | 2014-07-31 | 2019-10-11 | 南京中兴软件有限责任公司 | The generation method and device of alarm |
CN108259255B (en) * | 2016-12-29 | 2020-05-15 | 大唐移动通信设备有限公司 | Network element data analysis method and device |
US11630927B2 (en) * | 2019-10-15 | 2023-04-18 | Ruentex Engineering & Construction Co., Ltd. | Method and system for processing building energy information |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060092940A1 (en) * | 2004-11-01 | 2006-05-04 | Ansari Furquan A | Softrouter protocol disaggregation |
US20130223367A1 (en) * | 2012-02-29 | 2013-08-29 | Via Telecom, Inc. | Device and method for access probe enhancements |
US20140105218A1 (en) * | 2012-10-12 | 2014-04-17 | Prashant H. Anand | Queue monitoring to filter the trend for enhanced buffer management and dynamic queue threshold in 4g ip network/equipment for better traffic performance |
Family Cites Families (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FI107312B (en) * | 1997-10-14 | 2001-06-29 | Nokia Networks Oy | Network monitoring procedure for a telecommunications network |
ES2364747T3 (en) | 2001-08-24 | 2011-09-13 | Telefonaktiebolaget L M Ericsson (Publ) | PROCEDURE AND MEANS FOR REDISTRIBUTION OF SUBSCRIBER INFORMATION IN UMTS NETWORKS IN WHICH THE NODES ARE ARRANGED IN GROUPINGS. |
DE102005056250A1 (en) * | 2005-11-25 | 2007-05-31 | Siemens Ag | Computer system`s performance determining method, involves determining performance in form of current performance value of computer system in current configuration, and comparing current performance value with reference value |
CN101136805B (en) * | 2007-05-30 | 2010-06-09 | 中兴通讯股份有限公司 | Performance warning system and performance threshold obtaining method |
CN101384054B (en) | 2007-09-04 | 2012-01-11 | 中兴通讯股份有限公司 | Method for network exception condition monitoring through performance data |
CN101458634B (en) | 2008-01-22 | 2011-03-16 | 中兴通讯股份有限公司 | Load equilibration scheduling method and device |
US9274842B2 (en) | 2010-06-29 | 2016-03-01 | Microsoft Technology Licensing, Llc | Flexible and safe monitoring of computers |
CN101945407B (en) * | 2010-10-22 | 2012-11-28 | 东南大学 | Load balancing method for content monitoring of mobile service |
CN102232282B (en) | 2010-10-29 | 2014-03-26 | 华为技术有限公司 | Method and apparatus for realizing load balance of resources in data center |
CN102611564B (en) * | 2011-01-25 | 2017-04-05 | 中兴通讯股份有限公司 | A kind of method for realizing performance alarm, system and network element |
CN102932170B (en) * | 2012-10-22 | 2016-06-22 | 中兴通讯股份有限公司 | Network element load inequality detection processing method, device and system thereof |
-
2012
- 2012-10-22 CN CN201210404787.9A patent/CN102932170B/en not_active Expired - Fee Related
-
2013
- 2013-09-27 EP EP13849007.3A patent/EP2899918A4/en not_active Withdrawn
- 2013-09-27 WO PCT/CN2013/084512 patent/WO2014063557A1/en active Application Filing
- 2013-09-27 US US14/437,337 patent/US9674065B2/en not_active Expired - Fee Related
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060092940A1 (en) * | 2004-11-01 | 2006-05-04 | Ansari Furquan A | Softrouter protocol disaggregation |
US20130223367A1 (en) * | 2012-02-29 | 2013-08-29 | Via Telecom, Inc. | Device and method for access probe enhancements |
US20140105218A1 (en) * | 2012-10-12 | 2014-04-17 | Prashant H. Anand | Queue monitoring to filter the trend for enhanced buffer management and dynamic queue threshold in 4g ip network/equipment for better traffic performance |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11157323B2 (en) * | 2019-01-10 | 2021-10-26 | International Business Machines Corporation | Multiple metric based load prediction and resource allocation in an active stream processing job |
Also Published As
Publication number | Publication date |
---|---|
CN102932170A (en) | 2013-02-13 |
WO2014063557A1 (en) | 2014-05-01 |
CN102932170B (en) | 2016-06-22 |
EP2899918A4 (en) | 2015-10-21 |
EP2899918A1 (en) | 2015-07-29 |
US9674065B2 (en) | 2017-06-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9674065B2 (en) | Method, apparatus and system for detecting network element load imbalance | |
US10257216B2 (en) | Method and system for obtaining and analyzing forensic data in a distributed computer infrastructure | |
CN103220173B (en) | A kind of alarm monitoring method and supervisory control system | |
CN102932466B (en) | The distributed source method for supervising of content-based distributing network and system | |
US9015312B2 (en) | Network management system and method for identifying and accessing quality of service issues within a communications network | |
CN103491354A (en) | System operation monitoring and controlling visual platform | |
CN103544093A (en) | Monitoring and alarm control method and system | |
CN106487612A (en) | A kind of server node monitoring method, monitoring server and system | |
CN115038088B (en) | Intelligent network security detection early warning system and method | |
CN111192130A (en) | Method, system, device and storage medium for determining fault source in transaction monitoring | |
CN106453504A (en) | Monitoring system and method based on NGINX server cluster | |
CN107426051B (en) | The monitoring method of the working condition of distributed cluster system interior joint, apparatus and system | |
CN103763143A (en) | Method and system for equipment abnormality alarming based on storage server | |
WO2018035765A1 (en) | Method and apparatus for detecting network abnormity | |
CN109150626A (en) | FTP service monitoring method, device, terminal and computer readable storage medium | |
CN110730087A (en) | Method and device for processing alarm storm | |
CN112910733A (en) | Full link monitoring system and method based on big data | |
CN112291185B (en) | Method and device for collecting network data | |
CN110601885A (en) | Artificial intelligence public cloud abnormity indication alarm system | |
WO2024066404A1 (en) | Optical cable sag recognition method and device | |
KR102298907B1 (en) | Method And Apparatus For Monitoring Communication Service Failure | |
CN113890814B (en) | Fault perception model construction and fault perception method and system, equipment and medium | |
JP2019175070A (en) | Alert notification device and alert notification method | |
TWI749072B (en) | Abnormal traffic detecting server and abnormal traffic detecting method thereof | |
CN103401711A (en) | Security log-based network state analysis system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: ZTE CORPORATION, CHINA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:JIANG, CHUNHE;LIU, FENG;REEL/FRAME:035792/0054 Effective date: 20150407 |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
LAPS | Lapse for failure to pay maintenance fees |
Free format text: PATENT EXPIRED FOR FAILURE TO PAY MAINTENANCE FEES (ORIGINAL EVENT CODE: EXP.); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY |
|
FEPP | Fee payment procedure |
Free format text: MAINTENANCE FEE REMINDER MAILED (ORIGINAL EVENT CODE: REM.); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY |
|
STCH | Information on status: patent discontinuation |
Free format text: PATENT EXPIRED DUE TO NONPAYMENT OF MAINTENANCE FEES UNDER 37 CFR 1.362 |
|
FP | Lapsed due to failure to pay maintenance fee |
Effective date: 20210606 |